© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 117767
    Prev
    Next
    INDEX
    Explanations

    references to related articles or content prompts in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ril
    -0.07
    ÙĬا
    -0.07
    amp
    -0.07
    olk
    -0.06
    apis
    -0.06
    oningen
    -0.06
    _FACTOR
    -0.06
    ëĿ¼ìĿ¸
    -0.06
    _SECURITY
    -0.06
    ching
    -0.06
    POSITIVE LOGITS
    atts
    0.07
    dden
    0.07
    pollo
    0.07
    porno
    0.06
    aidu
    0.06
    chestra
    0.06
    din
    0.06
    ancell
    0.06
    lds
    0.06
    ouis
    0.06
    Activations Density 0.001%

    No Known Activations